??

.gitattributes

@@ -33,5 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-*.mp3 filter=lfs diff=lfs merge=lfs -text
 *.wav filter=lfs diff=lfs merge=lfs -text

.github/FUNDING.yml

@@ -1,13 +0,0 @@
-# These are supported funding model platforms
-
-github: [Pranjalya]
-patreon: # Replace with a single Patreon username
-open_collective: # Replace with a single Open Collective username
-ko_fi: # Replace with a single Ko-fi username
-tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
-community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
-liberapay: # Replace with a single Liberapay username
-issuehunt: # Replace with a single IssueHunt username
-otechie: # Replace with a single Otechie username
-lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
-custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.gitignore

@@ -1,135 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-pip-wheel-metadata/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-.python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-.idea/*
-.models/*
-.custom/*
-results/*
-debug_states/*

CITATION.cff

@@ -1,10 +0,0 @@
-cff-version: 1.3.0
-message: "If you use this software, please cite it as below."
-authors:
-- family-names: "Betker"
-  given-names: "James"
-  orcid: "https://orcid.org/my-orcid?orcid=0000-0003-3259-4862"
-title: "TorToiSe text-to-speech"
-version: 2.0
-date-released: 2022-04-28
-url: "https://github.com/neonbjb/tortoise-tts"

LICENSE

@@ -1,201 +0,0 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.

MANIFEST.in

@@ -1,2 +0,0 @@
-recursive-include tortoise/data *
-recursive-include tortoise/voices *

README.md

@@ -1,12 +1,13 @@
 ---
-title: Tortoise
-emoji: 😻
-colorFrom: red
-colorTo: purple
+title: Tortoise Tts
+emoji: 🐠
+colorFrom: gray
+colorTo: gray
 sdk: gradio
-sdk_version: 3.50.2
+sdk_version: 3.44.4
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,146 +1,151 @@
 import os
+import torch
 import gradio as gr
 import torchaudio
 import time
 from datetime import datetime
 from tortoise.api import TextToSpeech
+from tortoise.utils.text import split_and_recombine_text
 from tortoise.utils.audio import load_audio, load_voice, load_voices
 
 VOICE_OPTIONS = [
+    "angie",
+    "deniro",
+    "freeman",
+    "halle",
+    "lj",
+    "myself",
+    "pat2",
+    "snakes",
+    "tom",
+    "daws",
+    "dreams",
+    "grace",
+    "lescault",
+    "weaver",
+    "applejack",
+    "daniel",
+    "emma",
+    "geralt",
+    "jlaw",
+    "mol",
+    "pat",
+    "rainbow",
+    "tim_reynolds",
+    "atkins",
+    "dortice",
+    "empire",
+    "kennard",
+    "mouse",
+    "william",
+    "jane_eyre",
     "random",  # special option for random voice
-    "custom_voice",  # special option for custom voice
-    "disabled",  # special option for disabled voice
 ]
 
 
-def inference(text, emotion, prompt, voice, mic_audio, voice_b, voice_c, preset, seed):
-    if voice != "custom_voice":
-        voices = [voice]
+def inference(
+    text,
+    script,
+    voice,
+    voice_b,
+    seed,
+    split_by_newline,
+):
+    if text is None or text.strip() == "":
+        with open(script.name) as f:
+            text = f.read()
+        if text.strip() == "":
+            raise gr.Error("Please provide either text or script file with content.")
+
+    if split_by_newline == "Yes":
+        texts = list(filter(lambda x: x.strip() != "", text.split("\n")))
     else:
-        voices = []
+        texts = split_and_recombine_text(text)
 
+    voices = [voice]
     if voice_b != "disabled":
         voices.append(voice_b)
-    if voice_c != "disabled":
-        voices.append(voice_c)
 
-    if emotion != "None/Custom":
-        text = f"[I am really {emotion.lower()},] {text}"
-    elif prompt.strip() != "":
-        text = f"[{prompt},] {text}"
-
-    c = None
-    if voice == "custom_voice":
-        if mic_audio is None:
-            raise gr.Error("Please provide audio from mic when choosing custom voice")
-        c = load_audio(mic_audio, 22050)
-
-
-    if len(voices) == 1 or len(voices) == 0:
-        if voice == "custom_voice":
-            voice_samples, conditioning_latents = [c], None
-        else:
-            voice_samples, conditioning_latents = load_voice(voice)
+    if len(voices) == 1:
+        voice_samples, conditioning_latents = load_voice(voice)
     else:
         voice_samples, conditioning_latents = load_voices(voices)
-        if voice == "custom_voice":
-            voice_samples.extend([c])
-
-    sample_voice = voice_samples[0] if len(voice_samples) else None
 
     start_time = time.time()
-    gen, _ = tts.tts_with_preset(
-        text,
-        voice_samples=voice_samples,
-        conditioning_latents=conditioning_latents,
-        preset=preset,
-        use_deterministic_seed=seed,
-        return_deterministic_state=True,
-        k=3,
-    )
-
-    with open("Tortoise_TTS_Runs.log", "a") as f:
-        f.write(
-            f"{datetime.now()} | Voice: {','.join(voices)} | Text: {text} | Quality: {preset} | Time Taken (s): {time.time()-start_time} | Seed: {seed}\n"
-        )
-
-    return (
-        (22050, sample_voice.squeeze().cpu().numpy()),
-        (24000, gen[0].squeeze().cpu().numpy()),
-        (24000, gen[1].squeeze().cpu().numpy()),
-        (24000, gen[2].squeeze().cpu().numpy()),
-    )
-
 
+    # all_parts = []
+    for j, text in enumerate(texts):
+        for audio_frame in tts.tts_with_preset(
+            text,
+            voice_samples=voice_samples,
+            conditioning_latents=conditioning_latents,
+            preset="ultra_fast",
+            k=1
+        ):
+            # print("Time taken: ", time.time() - start_time)
+            # all_parts.append(audio_frame)
+            yield (24000, audio_frame.cpu().detach().numpy())
+
+    # wav = torch.cat(all_parts, dim=0).unsqueeze(0)
+    # print(wav.shape)
+    # torchaudio.save("output.wav", wav.cpu(), 24000)
+    # yield (None, gr.make_waveform(audio="output.wav",))
 def main():
-    text = gr.Textbox(lines=4, label="Text:")
-    emotion = gr.Radio(
-        ["None/Custom", "Happy", "Sad", "Angry", "Disgusted", "Arrogant"],
-        value="None/Custom",
-        label="Select emotion:",
-        type="value",
-    )
-    prompt = gr.Textbox(lines=1, label="Enter prompt if [Custom] emotion:")
-    preset = gr.Radio(
-        ["ultra_fast", "fast", "standard", "high_quality"],
-        value="fast",
-        label="Preset mode (determines quality with tradeoff over speed):",
-        type="value",
+    title = "Tortoise TTS 🐢"
+    description = """
+    A text-to-speech system which powers lot of organizations in Speech synthesis domain.
+    <br/>
+    a model with strong multi-voice capabilities, highly realistic prosody and intonation.
+    <br/>
+    for faster inference, use the 'ultra_fast' preset and duplicate space if you don't want to wait in a queue.
+    <br/>
+    """
+    text = gr.Textbox(
+        lines=4,
+        label="Text (Provide either text, or upload a newline separated text file below):",
     )
+    script = gr.File(label="Upload a text file")
+
     voice = gr.Dropdown(
-        os.listdir(os.path.join("tortoise", "voices")) + VOICE_OPTIONS,
-        value="angie",
-        label="Select voice:",
-        type="value",
-    )
-    mic_audio = gr.Audio(
-        label="Record voice (when selected custom_voice):",
-        source="microphone",
-        type="filepath",
+        VOICE_OPTIONS, value="jane_eyre", label="Select voice:", type="value"
     )
     voice_b = gr.Dropdown(
-        os.listdir(os.path.join("tortoise", "voices")) + VOICE_OPTIONS,
+        VOICE_OPTIONS,
         value="disabled",
         label="(Optional) Select second voice:",
         type="value",
     )
-    voice_c = gr.Dropdown(
-        os.listdir(os.path.join("tortoise", "voices")) + VOICE_OPTIONS,
-        value="disabled",
-        label="(Optional) Select third voice:",
+    split_by_newline = gr.Radio(
+        ["Yes", "No"],
+        label="Split by newline (If [No], it will automatically try to find relevant splits):",
         type="value",
+        value="No",
     )
-    seed = gr.Number(value=0, precision=0, label="Seed (for reproducibility):")
-
-    selected_voice = gr.Audio(label="Sample of selected voice (first):")
-    output_audio_1 = gr.Audio(label="Output [Candidate 1]:")
-    output_audio_2 = gr.Audio(label="Output [Candidate 2]:")
-    output_audio_3 = gr.Audio(label="Output [Candidate 3]:")
 
+    output_audio = gr.Audio(label="streaming audio:", streaming=True, autoplay=True)
+    # download_audio = gr.Audio(label="dowanload audio:")
     interface = gr.Interface(
         fn=inference,
         inputs=[
             text,
-            emotion,
-            prompt,
+            script,
             voice,
-            mic_audio,
             voice_b,
-            voice_c,
-            preset,
-            seed,
+            split_by_newline,
         ],
-        outputs=[selected_voice, output_audio_1, output_audio_2, output_audio_3],
+        title=title,
+        description=description,
+        outputs=[output_audio],
     )
-    interface.launch(share=True)
+    interface.queue().launch()
 
 
 if __name__ == "__main__":
-    tts = TextToSpeech()
+    tts = TextToSpeech(kv_cache=True, use_deepspeed=True, half=True)
 
-    with open("Tortoise_TTS_Runs.log", "a") as f:
+    with open("Tortoise_TTS_Runs_Scripts.log", "a") as f:
         f.write(
-            f"\n\n-------------------------Tortoise TTS Logs, {datetime.now()}-------------------------\n"
+            f"\n\n-------------------------Tortoise TTS Scripts Logs, {datetime.now()}-------------------------\n"
         )
 
-    main()
+    main()

app_read.py

@@ -1,204 +0,0 @@
-import os
-import torch
-import gradio as gr
-import torchaudio
-import time
-from datetime import datetime
-from tortoise.api import TextToSpeech
-from tortoise.utils.text import split_and_recombine_text
-from tortoise.utils.audio import load_audio, load_voice, load_voices
-
-VOICE_OPTIONS = [
-    # "raider_male",
-    "sebastian",
-    # "jacoren",
-    # "cond_latent_example",
-    # "deniro",
-    # "freeman",
-    # "halle",
-    # "lj",
-    # "myself",
-    # "pat2",
-    # "snakes",
-    # "tom",
-    # "train_daws",
-    # "train_dreams",
-    # "train_grace",
-    # "train_lescault",
-    # "weaver",
-    # "applejack",
-    # "daniel",
-    # "emma",
-    # "geralt",
-    # "jlaw",
-    # "mol",
-    # "pat",
-    # "rainbow",
-    # "tim_reynolds",
-    # "train_atkins",
-    # "train_dotrice",
-    # "train_empire",
-    # "train_kennard",
-    # "train_mouse",
-    # "william",
-    "random",  # special option for random voice
-    "custom_voice",  # special option for custom voice
-    "disabled",  # special option for disabled voice
-]
-
-
-def inference(
-    text,
-    script,
-    name,
-    voice,
-    voice_b,
-    voice_c,
-    preset,
-    seed,
-    regenerate,
-    split_by_newline,
-):
-    if regenerate.strip() == "":
-        regenerate = None
-
-    if name.strip() == "":
-        raise gr.Error("No name provided")
-
-    if text is None or text.strip() == "":
-        with open(script.name) as f:
-            text = f.read()
-        if text.strip() == "":
-            raise gr.Error("Please provide either text or script file with content.")
-
-    if split_by_newline == "Yes":
-        texts = list(filter(lambda x: x.strip() != "", text.split("\n")))
-    else:
-        texts = split_and_recombine_text(text)
-
-    os.makedirs(os.path.join("longform", name), exist_ok=True)
-
-    if regenerate is not None:
-        regenerate = list(map(int, regenerate.split()))
-
-    voices = [voice]
-    if voice_b != "disabled":
-        voices.append(voice_b)
-    if voice_c != "disabled":
-        voices.append(voice_c)
-
-    if len(voices) == 1:
-        voice_samples, conditioning_latents = load_voice(voice)
-    else:
-        voice_samples, conditioning_latents = load_voices(voices)
-
-    start_time = time.time()
-
-    all_parts = []
-    for j, text in enumerate(texts):
-        if regenerate is not None and j + 1 not in regenerate:
-            all_parts.append(
-                load_audio(os.path.join("longform", name, f"{j+1}.wav"), 24000)
-            )
-            continue
-        gen = tts.tts_with_preset(
-            text,
-            voice_samples=voice_samples,
-            conditioning_latents=conditioning_latents,
-            preset=preset,
-            k=1,
-            use_deterministic_seed=seed,
-        )
-
-        gen = gen.squeeze(0).cpu()
-        torchaudio.save(os.path.join("longform", name, f"{j+1}.wav"), gen, 24000)
-
-        all_parts.append(gen)
-
-    full_audio = torch.cat(all_parts, dim=-1)
-
-    os.makedirs("outputs", exist_ok=True)
-    torchaudio.save(os.path.join("outputs", f"{name}.wav"), full_audio, 24000)
-
-    with open("Tortoise_TTS_Runs_Scripts.log", "a") as f:
-        f.write(
-            f"{datetime.now()} | Voice: {','.join(voices)} | Text: {text} | Quality: {preset} | Time Taken (s): {time.time()-start_time} | Seed: {seed}\n"
-        )
-
-    output_texts = [f"({j+1}) {texts[j]}" for j in range(len(texts))]
-
-    return ((24000, full_audio.squeeze().cpu().numpy()), "\n".join(output_texts))
-
-
-def main():
-    text = gr.Textbox(
-        lines=4,
-        label="Text (Provide either text, or upload a newline separated text file below):",
-    )
-    script = gr.File(label="Upload a text file")
-    name = gr.Textbox(
-        lines=1, label="Name of the output file / folder to store intermediate results:"
-    )
-    preset = gr.Radio(
-        ["ultra_fast", "fast", "standard", "high_quality"],
-        value="fast",
-        label="Preset mode (determines quality with tradeoff over speed):",
-        type="value",
-    )
-    voice = gr.Dropdown(
-        VOICE_OPTIONS, value="angie", label="Select voice:", type="value"
-    )
-    voice_b = gr.Dropdown(
-        VOICE_OPTIONS,
-        value="disabled",
-        label="(Optional) Select second voice:",
-        type="value",
-    )
-    voice_c = gr.Dropdown(
-        VOICE_OPTIONS,
-        value="disabled",
-        label="(Optional) Select third voice:",
-        type="value",
-    )
-    seed = gr.Number(value=0, precision=0, label="Seed (for reproducibility):")
-    regenerate = gr.Textbox(
-        lines=1,
-        label="Comma-separated indices of clips to regenerate [starting from 1]",
-    )
-    split_by_newline = gr.Radio(
-        ["Yes", "No"],
-        label="Split by newline (If [No], it will automatically try to find relevant splits):",
-        type="value",
-        value="No",
-    )
-    output_audio = gr.Audio(label="Combined audio:")
-    output_text = gr.Textbox(label="Split texts with indices:", lines=10)
-
-    interface = gr.Interface(
-        fn=inference,
-        inputs=[
-            text,
-            script,
-            name,
-            voice,
-            voice_b,
-            voice_c,
-            preset,
-            seed,
-            regenerate,
-            split_by_newline,
-        ],
-        outputs=[output_audio, output_text],
-    )
-    interface.launch(share=False)
-
-
-if __name__ == "__main__":
-    tts = TextToSpeech()
-
-    with open("Tortoise_TTS_Runs_Scripts.log", "a") as f:
-        f.write(
-            f"\n\n-------------------------Tortoise TTS Scripts Logs, {datetime.now()}-------------------------\n"
-        )
-
-    main()

examples/favorites/daniel_craig_dumbledore.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:38328f3120a18bbbd170caf9ae9faaa623a34f644d86b5a9a750095945d0ed2a
-size 24045

examples/favorites/daniel_craig_training_ethics.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4d399b8ec06d55fd621d772ebd86637801ac1651698e633758e6f5540065d2d8
-size 48909

examples/favorites/dotrice_stop_for_death.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fb1eaf0db9bcc46efbd4268df8e1ae96defc5e173645380089dc8defd5c76093
-size 28845

examples/favorites/emma_stone_courage.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3b2e92946410033681a3f156e3084e3f1d240437bebd00e9d8641b4127dac027
-size 34125

examples/favorites/emma_stone_training_ethics.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0310203f39c3fe0ecb7ec5182970d50a2db4b14a67798e76535f8e7b3a15dcf8
-size 48045

examples/favorites/halle_barry_dumbledore.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:57901a5e7b475a45b6842947c49370f264cc391cfd59ec0c6af6f2ec0fbe1342
-size 21453

examples/favorites/halle_barry_oar_to_oar.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dff5e42f46f0ed2ab27c070d75c0f8daf32b81d98f1e9c08cc901a7f4cf76932
-size 40941

examples/favorites/henry_cavill_metallic_hydrogen.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9deecc64d009576b6ffe0d993a1655cf2c5954b963e1f7c7a3c9a82a8ce73a67
-size 32013

examples/favorites/kennard_road_not_taken.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3639a696e552fad795a2ade069da7bf74ca0f49acb895d73996a30102509ebd4
-size 28461

examples/favorites/morgan_freeman_metallic_hydrogen.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d9d1e4d78fe34654336ca28427a3cbc719e524c6536d0668ceb9b7ed5ca33800
-size 35373

examples/favorites/myself_gatsby.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b2d669935ebf1a525524736729e7873d278e3ab09bf2f38e822d43436ef916b8
-size 28077

examples/favorites/patrick_stewart_omicron.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b1af89a730eaa532f99e04b6dd2b68ac94607bac574cb24de1a97a9a74f713ca
-size 37581

examples/favorites/patrick_stewart_secret_of_life.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7a324fcc4b320cda9eba9b0ee9b74f22ff2e3ece03b54cbef2984865879abb88
-size 36525

examples/favorites/robert_deniro_review.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:057b5cfd29d82cb5774e15dff8b613d0b8ab9d61ce486caf5acd4b952d67b92f
-size 36141

examples/favorites/william_shatner_spacecraft_interview.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f8c001c8602900e2afd8e15a9b499520c090aaa5db7c8c28ad8343ae5c166a1a
-size 47277

examples/finetuned/lj/1.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4928bae791bcf583b4527fcf6ad45fc51da67973fe04c4b76bd3c6cdba5e8f77
-size 38157

examples/finetuned/lj/2.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c647d43d52092244f8ef78598243a0fc4e24394dc8224cca4a1a8c700c45a4a7
-size 26061

examples/finetuned/lj/3.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f46328a5b9a342471904ad3215bb6302cc30e094d250bce1ec69b5a6c4772768
-size 18477

examples/finetuned/lj/4.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fb7cc0ff61c490bbf8b8638b37eee656cf00e6095e9bcbb99a913134f6f7ae81
-size 22893

examples/naturalspeech_comparison/fibers/naturalspeech.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:985c17d9f66813fe5d91cb466f6ab614e8413241527d78f2525bd6a2a3ab92ab
-size 33141

examples/naturalspeech_comparison/fibers/tortoise.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1f381fa7eadd8c4c23955e48de770dc49bc8ca8237b380104bae5ea7d8b6bdc9
-size 33453

examples/naturalspeech_comparison/lax/naturalspeech.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe249b3fcc06d08c4241720d7768108e91062ee53d308d30fb484f97085cc4e6
-size 40978

examples/naturalspeech_comparison/lax/tortoise.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:44c43087fab836c25d46e4b1ca6afecc8f745e58dad721aae15cf989f76954f5
-size 42285

examples/naturalspeech_comparison/maltby/naturalspeech.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d37bce11874d87ab46fe3614df2535ce6c22a35dbd2c8df9582386e57c5a3e5f
-size 35127

examples/naturalspeech_comparison/maltby/tortoise.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2dc181b24f72a7fa8d6442b19eef876c4b16454aaf7c90f9f8e2afd13cf80b38
-size 36909

examples/prompting/angry.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:57130e4861e39e2d51146cfc692f7bfb6d7dec6942add307a3ca1f408494f82d
-size 7629

examples/prompting/happy.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:99cd3b7c3fdfbc262573a925e0bde004e9fd589922804b2c209c68ae1bb5a6ca
-size 8301

examples/prompting/sad.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae16ffd08f0ef5024c151d4ba6bb2bea6cb213ce3f1241da89198fe2a6e03072
-size 6285

examples/prompting/scared.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1a58a4bd50daad256380435bec57dedf16b017c587c6e94f5127019ea89762f4
-size 6861

examples/riding_hood/angelina.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:413942dd8441d499c6752ecd9f3cd790f2a8af00e90881b3d8ff2db0f4834e03
-size 866157

examples/riding_hood/craig.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:52c635563ae37c6cead2beb599245847df40866fe534cc68551d733b500e1013
-size 825645

examples/riding_hood/deniro.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ac83e5a28120d31af57f05a87663136cd9227c3c685c3b3d334c250431033463
-size 851181

examples/riding_hood/emma.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a617489873ae94dc607dbae7156d4ae29835a89f2e5ad7e95952bdf94e6369c0
-size 807309

examples/riding_hood/freeman.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e5c38334b399b713850161eaddbffb128b65d8dc98deb67c642b355fd080d585
-size 942765

examples/riding_hood/geralt.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a5f4c4872c48166f1532a2d2cbb3b6aa6453d4f965cddf6da76403a5d18398d6
-size 788493

examples/riding_hood/halle.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bae0d09786663b56fd72e594dfd275efc02589370957e34469ad0becc874b88c
-size 785229

examples/riding_hood/jlaw.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:83eab02adec8b129c0a2c5dc4abad3a5646b0f6de16a3d0ec35fd4263ea5a8bf
-size 666861

examples/riding_hood/lj.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0eadb7a268ad3ac785986f3f925eec49d47bdef19899f109cced14086b359644
-size 817293

examples/riding_hood/myself.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8562d661e13bef6f4f3dbcfc0cfb54f236e277ff5b75e6feab6f6b6a15fd42f8
-size 950637

examples/riding_hood/pat.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:26f671fdcbfa9887db08e381c2b74ba65aea42f00a20b1c40a24a1ee35a3bc34
-size 886509

examples/riding_hood/snakes.mp3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d89c224f034c8b847a6236b77a491c0b532104a844097f7cd6daa5cb529e2423
-size 790125